competitive-report-structure
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [NO_CODE]: The skill is comprised entirely of Markdown instructions, workflow definitions, and report templates. It does not include any executable code (Python, JavaScript, or shell scripts) or platform-specific command triggers.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a data processor for external content, creating a surface for potential instruction injection through ingested data.
- Ingestion points: The skill specifically processes competitor profile cards from
benchmark-methodology, client positioning briefs, and research source notes. - Boundary markers: There are no explicit instructions or delimiters provided to prevent the agent from obeying instructions that might be embedded within the competitive research data.
- Capability inventory: The skill's capabilities are restricted to reading local data, searching, and drafting report content; it lacks capabilities for arbitrary file writing or network exfiltration.
- Sanitization: No sanitization or validation logic is defined for the content extracted from external research sources.
Audit Metadata